Artificial neural network application in analog layout placement design

Abstract

In this paper, we propose a method using mean-field neural networks to solve the placement problem for the layout design of analog integrated circuits. By means of the energy function, our method can not only meet the basic requirements of placement, but also handle the symmetry and proximity constraints that are special for analog layouts. Compared with other work, our experimental results show this proposed optimization scheme can achieve more efficient performance and obtain optimal solutions.